Triple
T4253670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sepik River |
E95917
|
entity |
| Predicate | majorSettlementOn |
P13187
|
FINISHED |
| Object |
Ambunti
Ambunti is a small riverside town in East Sepik Province, Papua New Guinea, known as a key local hub for communities along the middle Sepik River.
|
E423434
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Ambunti | Statement: [Sepik River, majorSettlementOn, Ambunti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ambunti Context triple: [Sepik River, majorSettlementOn, Ambunti]
-
A.
Ambo
Ambo is a coastal village on Tarawa Atoll in Kiribati, known for its role as a small residential and administrative community in the central Pacific.
-
B.
Landana
Landana is a coastal town in Angola’s Cabinda exclave, historically known as a regional trading and missionary center.
-
C.
Baniata
Baniata is an Oceanic language of the Meso-Melanesian group spoken in the Solomon Islands.
-
D.
Amarar
Amarar is the native name used by the Beja people to refer to themselves or their community.
-
E.
Annino
Annino is a Moscow Metro station on the Serpukhovsko–Timiryazevskaya Line serving the Annino district in southern Moscow.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Ambunti Triple: [Sepik River, majorSettlementOn, Ambunti]
Generated description
Ambunti is a small riverside town in East Sepik Province, Papua New Guinea, known as a key local hub for communities along the middle Sepik River.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ambunti Target entity description: Ambunti is a small riverside town in East Sepik Province, Papua New Guinea, known as a key local hub for communities along the middle Sepik River.
-
A.
Ambo
Ambo is a coastal village on Tarawa Atoll in Kiribati, known for its role as a small residential and administrative community in the central Pacific.
-
B.
Landana
Landana is a coastal town in Angola’s Cabinda exclave, historically known as a regional trading and missionary center.
-
C.
Baniata
Baniata is an Oceanic language of the Meso-Melanesian group spoken in the Solomon Islands.
-
D.
Amarar
Amarar is the native name used by the Beja people to refer to themselves or their community.
-
E.
Annino
Annino is a Moscow Metro station on the Serpukhovsko–Timiryazevskaya Line serving the Annino district in southern Moscow.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69b3453f759881909b91f01a1e82c036 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34f7d20b48190a404638c68c31026 |
completed | March 12, 2026, 11:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5a8845e6081908bbf1aef2a2da754 |
completed | March 14, 2026, 6:27 p.m. |
| NEDg | Description generation | batch_69b5a8f374fc8190830286dfadc9bdbb |
completed | March 14, 2026, 6:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5a99c9310819084b973aecb1886fe |
completed | March 14, 2026, 6:31 p.m. |
Created at: March 12, 2026, 11:06 p.m.